Correlation of two random variables

 

Correlation between two random variables is a number between –1 and +1

 

0 Correlation means that there is NO predictive connection between them

*        the outcome of one variable tells you nothing about the outcome of the other variable

 

+ Correlation means that the outcomes tend to move in the same direction

*        outcome of one variable higher than expected tells you that the outcome of the other variable will tend to be higher than expected

*        outcome of one variable lower than expected tells you that outcome of the other variable will tend to be lower than expected

*        +1 correlation tells you the tendency is almost certain

 

– Correlation means that the outcomes tend to move in opposite directions

*        outcome of one variable higher than expected tells you that the outcome of the other variable will tend to be lower than expected

*        outcome of one variable lower than expected tells you that the outcome of the other variable will tend to be higher than expected

*        –1 correlation tells you tendency is almost certain

 

Pooling of Risks

 

Pooling two risks (random variables; uncertain outcomes) means that each agrees to bear half of the total of the two outcomes … each bears the average outcome.  One Participant    Two Participants

 

If identical risks are pooled the example shows that:

*        the expected value doesn’t change

 

If the risks are also uncorrelated (0 correlation, independent):

*        the variance (std deviation; “risk”) is lower

*        relatively more probability winds up closer to the expected value Two Participants

*        total outcome easier to predict than separate outcomes

*        share of the total easier to predict than separate outcome

 

POOLING REDUCES RISK FOR EACH PARTICIPANT WHEN THE PARTICIPATING RISKS ARE UNCORRELATED

*         the example was identical risks but so long as they are uncorrelated, within reason, similar but non-identical risks work the same way … just assign each its expected share of the total expected value (give a quick example) … that’s part of underwriting

 

The more uncorrelated risks being pooled, the greater the effect Four Participants   Lots of Participants

 

The law of large numbers says that the larger the number of uncorrelated risks, the more the probability of the average outcome (the “pooled” outcome) gets concentrated close to the expected value (draw a graph)

*        but don’t forget, in the real world you usually don’t know the expected value with perfect accuracy

 

The central limit theorem says that the larger the number of uncorrelated risks, the more the probability distribution of the average outcome (the “pooled” outcome) looks like a normal distribution

*        the central limit theorem can fail to be true if the initial distribution (the one that applies to each risk separately) is too extreme … even though the law of large numbers will still apply, the probability distribution of the average outcome can be skewed rather than normal in these extreme cases

*        some insurance risks are suspected to be too extreme for the central limit theorem to apply

 

What If The Risks Are Not Uncorrelated?

 

First, what would cause risks to be positively correlated?  Underwriting (more later) tries to fight these causes of positive correlation (for most risk management, don’t worry about negative correlation – the world isn’t that kind to us)

*        a common event causes or affects more than one of the risks

§        one conflagration burns many buildings (the old map clerk; reinsurance) – affects frequency

§        one hurricane damages many properties (coastal underwriting control; reinsurance) – affects frequency and severity

§        one accident causes many injuries and/or deaths (WTC) – frequency and severity (double indemnity)

§        one epidemic causes many illnesses and/or deaths (1918-19 flu; AIDS) – frequency and maybe severity

*        a common process influences more than one risk simultaneously

§        inflation raises all loss costs (replacement and/or service costs) more than expected – severity

§        litigious attitude spreads in society faster than expected – frequency and/or severity

§        tendency of people to use healthcare services increases faster than expected – frequency and/or severity

 

What does positive correlation do to pooling?

*        It erases some of the risk-reduction (draw graph)

*        Not all of it (unless the correlation goes to +1) (draw graph)

*        It works just as if fewer risks were in the pool in the first place

 

A major challenge for pooling is to keep correlation at bay as much as possible

 

Costs of Pooling  (also called “contracting costs”)

 

Distribution Costs and Function – SELLING

*        Independent agents/brokers; exclusive (tied) agents/employees; direct response channels (now including web)

*        Obvious function: get plenty of participants into the pool

*        Equally important:

§        get uncorrelated participants – to protect true pooling and ensure risk (variance) reduction

§        get (select) participants who didn’t just search out the pool in order to take advantage of it (called anti-selection) – to protect the average outcome; (don’t sell insurance to anyone who wants it too badly, instead you want slightly reluctant participants whom your sales effort has uncovered and convinced to join)

*        Whole life insurance distribution costs can chew up the whole first year premium – roughly equal in value to avoiding one “extra” death per thousand per year

 

Underwriting Costs and Function – SELECTION & PRICING

*        Skilled employees; organized rules, processes and discipline (now including artificial intelligence technology); investigation and data collection (now including data mining); bureaus/services

*        Obvious function: discover and turn away participants attempting to take advantage of the pool (i.e. fight anti-selection)

*        Equally important:

§        assign each participant reasonably accurately to a group with similar expected costs and risk (classification and pricing)

§        screen participants and the terms of pooling (the contracts) to avoid creating incentives to behave in ways that threaten the pool (moral hazard)

 

Loss Adjustment Costs and Function – INVESTIGATION&SETTLEMENT

*        Investigators, decision-makers, and lawyers; employees and outside services/firms; investigation, evaluation, negotiation, litigation, and agreement

*        Obvious function: detect frauds and assign fair value to legitimate losses; handle the resulting payments

*        Equally important:

§        diminish moral hazards (exaggeration of losses, behavioral increase to losses – e.g. disability income claim)

§        sentinel effect – handle today’s claims in a way that makes tomorrow’s claimants/lawyers less likely to abuse the system

§        in a pure pooling system (more theoretical than realistic): assign and collect the assessments to pay for the losses

 

Premium Administration – ASSESSMENT & COLLECTION

*        Ex post assessment of loss costs usually difficult/impossible

*        Ex ante assessment of “expected” loss costs works – called “premiums”

*        Requires expert data collection, analysis, projection and assessment skills: underwriters and actuaries; also administration of the collection and recordkeeping

*        Obvious function: assess total premiums enough to cover total “expected” losses plus required loadings

*        Equally important: maintain reasonable enough relationship between each participant’s premium and expected losses to avoid an anti-selection spiral

*        Subject both to sheer error and to residual uncertainty risk – what if not enough is assessed and collected?  Can’t go back ex post

 

INSURANCE = POOLING PLUS CAPITAL

 

Insurance institution capital stands behind any shortfall

*        Excess of economic value of assets over economic value of liabilities – might not equal the accounting book values

*        It’s like collateral for the promised loss payments

 

Since no insurance institution’s capital is infinite (U.S. gov’t.?) there remains some residual uncertainty risk when insurance is used to manage risk … risk manager (maybe with agent/broker help) needs to assess that risk

*        Insurance companies can and do become insolvent and fail to make promised loss payments (more in later classes about mechanisms to avoid that … but they are not 100% fail-safe)